Training in progress, epoch 2
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63115591d1dcab868b0f4a7ca8560862e3b97be42e476adb45b35b59172e9e89
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac23679a8a9e60ba58c56e8a0eecdaa697c63cdf8889039fb940a5d06ae0cbe6
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c4d5a271b775e49974806614e9aa83f4f0340a33d8e50c0545c5ec9842eec0
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42cd54f7fa07a64717be39d36e7d981685ffb209ad37620c7b28bac239f8556f
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -41,3 +41,43 @@
|
|
| 41 |
{"current_steps": 400, "total_steps": 1182, "loss": 0.5373, "learning_rate": 5e-06, "epoch": 1.015228426395939, "percentage": 33.84, "elapsed_time": "0:46:28", "remaining_time": "1:30:51"}
|
| 42 |
{"current_steps": 410, "total_steps": 1182, "loss": 0.5236, "learning_rate": 5e-06, "epoch": 1.0406091370558375, "percentage": 34.69, "elapsed_time": "0:47:30", "remaining_time": "1:29:27"}
|
| 43 |
{"current_steps": 420, "total_steps": 1182, "loss": 0.5279, "learning_rate": 5e-06, "epoch": 1.0659898477157361, "percentage": 35.53, "elapsed_time": "0:48:33", "remaining_time": "1:28:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
{"current_steps": 400, "total_steps": 1182, "loss": 0.5373, "learning_rate": 5e-06, "epoch": 1.015228426395939, "percentage": 33.84, "elapsed_time": "0:46:28", "remaining_time": "1:30:51"}
|
| 42 |
{"current_steps": 410, "total_steps": 1182, "loss": 0.5236, "learning_rate": 5e-06, "epoch": 1.0406091370558375, "percentage": 34.69, "elapsed_time": "0:47:30", "remaining_time": "1:29:27"}
|
| 43 |
{"current_steps": 420, "total_steps": 1182, "loss": 0.5279, "learning_rate": 5e-06, "epoch": 1.0659898477157361, "percentage": 35.53, "elapsed_time": "0:48:33", "remaining_time": "1:28:05"}
|
| 44 |
+
{"current_steps": 430, "total_steps": 1182, "loss": 0.5253, "learning_rate": 5e-06, "epoch": 1.0913705583756346, "percentage": 36.38, "elapsed_time": "0:49:35", "remaining_time": "1:26:43"}
|
| 45 |
+
{"current_steps": 440, "total_steps": 1182, "loss": 0.5224, "learning_rate": 5e-06, "epoch": 1.116751269035533, "percentage": 37.23, "elapsed_time": "0:50:38", "remaining_time": "1:25:23"}
|
| 46 |
+
{"current_steps": 450, "total_steps": 1182, "loss": 0.5196, "learning_rate": 5e-06, "epoch": 1.1421319796954315, "percentage": 38.07, "elapsed_time": "0:51:41", "remaining_time": "1:24:04"}
|
| 47 |
+
{"current_steps": 460, "total_steps": 1182, "loss": 0.5225, "learning_rate": 5e-06, "epoch": 1.16751269035533, "percentage": 38.92, "elapsed_time": "0:52:43", "remaining_time": "1:22:45"}
|
| 48 |
+
{"current_steps": 470, "total_steps": 1182, "loss": 0.5213, "learning_rate": 5e-06, "epoch": 1.1928934010152283, "percentage": 39.76, "elapsed_time": "0:53:46", "remaining_time": "1:21:27"}
|
| 49 |
+
{"current_steps": 480, "total_steps": 1182, "loss": 0.5216, "learning_rate": 5e-06, "epoch": 1.218274111675127, "percentage": 40.61, "elapsed_time": "0:54:48", "remaining_time": "1:20:09"}
|
| 50 |
+
{"current_steps": 490, "total_steps": 1182, "loss": 0.5176, "learning_rate": 5e-06, "epoch": 1.2436548223350254, "percentage": 41.46, "elapsed_time": "0:55:51", "remaining_time": "1:18:52"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 1182, "loss": 0.5221, "learning_rate": 5e-06, "epoch": 1.2690355329949239, "percentage": 42.3, "elapsed_time": "0:56:53", "remaining_time": "1:17:35"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 1182, "loss": 0.5238, "learning_rate": 5e-06, "epoch": 1.2944162436548223, "percentage": 43.15, "elapsed_time": "0:57:56", "remaining_time": "1:16:21"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 1182, "loss": 0.5171, "learning_rate": 5e-06, "epoch": 1.3197969543147208, "percentage": 43.99, "elapsed_time": "0:58:59", "remaining_time": "1:15:05"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 1182, "loss": 0.5173, "learning_rate": 5e-06, "epoch": 1.3451776649746192, "percentage": 44.84, "elapsed_time": "1:00:01", "remaining_time": "1:13:50"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 1182, "loss": 0.5183, "learning_rate": 5e-06, "epoch": 1.3705583756345177, "percentage": 45.69, "elapsed_time": "1:01:04", "remaining_time": "1:12:36"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 1182, "loss": 0.5131, "learning_rate": 5e-06, "epoch": 1.3959390862944163, "percentage": 46.53, "elapsed_time": "1:02:06", "remaining_time": "1:11:22"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 1182, "loss": 0.5145, "learning_rate": 5e-06, "epoch": 1.4213197969543148, "percentage": 47.38, "elapsed_time": "1:03:10", "remaining_time": "1:10:09"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 1182, "loss": 0.5148, "learning_rate": 5e-06, "epoch": 1.4467005076142132, "percentage": 48.22, "elapsed_time": "1:04:12", "remaining_time": "1:08:56"}
|
| 59 |
+
{"current_steps": 580, "total_steps": 1182, "loss": 0.5127, "learning_rate": 5e-06, "epoch": 1.4720812182741116, "percentage": 49.07, "elapsed_time": "1:05:15", "remaining_time": "1:07:43"}
|
| 60 |
+
{"current_steps": 590, "total_steps": 1182, "loss": 0.5139, "learning_rate": 5e-06, "epoch": 1.49746192893401, "percentage": 49.92, "elapsed_time": "1:06:17", "remaining_time": "1:06:30"}
|
| 61 |
+
{"current_steps": 600, "total_steps": 1182, "loss": 0.5109, "learning_rate": 5e-06, "epoch": 1.5228426395939088, "percentage": 50.76, "elapsed_time": "1:07:19", "remaining_time": "1:05:18"}
|
| 62 |
+
{"current_steps": 610, "total_steps": 1182, "loss": 0.5108, "learning_rate": 5e-06, "epoch": 1.548223350253807, "percentage": 51.61, "elapsed_time": "1:08:22", "remaining_time": "1:04:06"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 1182, "loss": 0.5105, "learning_rate": 5e-06, "epoch": 1.5736040609137056, "percentage": 52.45, "elapsed_time": "1:09:24", "remaining_time": "1:02:54"}
|
| 64 |
+
{"current_steps": 630, "total_steps": 1182, "loss": 0.5091, "learning_rate": 5e-06, "epoch": 1.598984771573604, "percentage": 53.3, "elapsed_time": "1:10:26", "remaining_time": "1:01:43"}
|
| 65 |
+
{"current_steps": 640, "total_steps": 1182, "loss": 0.5104, "learning_rate": 5e-06, "epoch": 1.6243654822335025, "percentage": 54.15, "elapsed_time": "1:11:29", "remaining_time": "1:00:32"}
|
| 66 |
+
{"current_steps": 650, "total_steps": 1182, "loss": 0.5119, "learning_rate": 5e-06, "epoch": 1.649746192893401, "percentage": 54.99, "elapsed_time": "1:12:32", "remaining_time": "0:59:22"}
|
| 67 |
+
{"current_steps": 660, "total_steps": 1182, "loss": 0.5163, "learning_rate": 5e-06, "epoch": 1.6751269035532994, "percentage": 55.84, "elapsed_time": "1:13:35", "remaining_time": "0:58:11"}
|
| 68 |
+
{"current_steps": 670, "total_steps": 1182, "loss": 0.5035, "learning_rate": 5e-06, "epoch": 1.700507614213198, "percentage": 56.68, "elapsed_time": "1:14:38", "remaining_time": "0:57:02"}
|
| 69 |
+
{"current_steps": 680, "total_steps": 1182, "loss": 0.5034, "learning_rate": 5e-06, "epoch": 1.7258883248730963, "percentage": 57.53, "elapsed_time": "1:15:41", "remaining_time": "0:55:52"}
|
| 70 |
+
{"current_steps": 690, "total_steps": 1182, "loss": 0.5071, "learning_rate": 5e-06, "epoch": 1.751269035532995, "percentage": 58.38, "elapsed_time": "1:16:43", "remaining_time": "0:54:42"}
|
| 71 |
+
{"current_steps": 700, "total_steps": 1182, "loss": 0.5071, "learning_rate": 5e-06, "epoch": 1.7766497461928934, "percentage": 59.22, "elapsed_time": "1:17:47", "remaining_time": "0:53:33"}
|
| 72 |
+
{"current_steps": 710, "total_steps": 1182, "loss": 0.5094, "learning_rate": 5e-06, "epoch": 1.8020304568527918, "percentage": 60.07, "elapsed_time": "1:18:50", "remaining_time": "0:52:24"}
|
| 73 |
+
{"current_steps": 720, "total_steps": 1182, "loss": 0.5075, "learning_rate": 5e-06, "epoch": 1.8274111675126905, "percentage": 60.91, "elapsed_time": "1:19:53", "remaining_time": "0:51:15"}
|
| 74 |
+
{"current_steps": 730, "total_steps": 1182, "loss": 0.5056, "learning_rate": 5e-06, "epoch": 1.8527918781725887, "percentage": 61.76, "elapsed_time": "1:20:56", "remaining_time": "0:50:06"}
|
| 75 |
+
{"current_steps": 740, "total_steps": 1182, "loss": 0.5126, "learning_rate": 5e-06, "epoch": 1.8781725888324874, "percentage": 62.61, "elapsed_time": "1:21:58", "remaining_time": "0:48:57"}
|
| 76 |
+
{"current_steps": 750, "total_steps": 1182, "loss": 0.5094, "learning_rate": 5e-06, "epoch": 1.9035532994923858, "percentage": 63.45, "elapsed_time": "1:23:00", "remaining_time": "0:47:48"}
|
| 77 |
+
{"current_steps": 760, "total_steps": 1182, "loss": 0.5111, "learning_rate": 5e-06, "epoch": 1.9289340101522843, "percentage": 64.3, "elapsed_time": "1:24:03", "remaining_time": "0:46:40"}
|
| 78 |
+
{"current_steps": 770, "total_steps": 1182, "loss": 0.4992, "learning_rate": 5e-06, "epoch": 1.9543147208121827, "percentage": 65.14, "elapsed_time": "1:25:05", "remaining_time": "0:45:31"}
|
| 79 |
+
{"current_steps": 780, "total_steps": 1182, "loss": 0.5073, "learning_rate": 5e-06, "epoch": 1.9796954314720812, "percentage": 65.99, "elapsed_time": "1:26:07", "remaining_time": "0:44:23"}
|
| 80 |
+
{"current_steps": 788, "total_steps": 1182, "eval_loss": 0.5355119109153748, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:27:32", "remaining_time": "0:43:46"}
|
| 81 |
+
{"current_steps": 790, "total_steps": 1182, "loss": 0.5004, "learning_rate": 5e-06, "epoch": 2.00507614213198, "percentage": 66.84, "elapsed_time": "1:31:34", "remaining_time": "0:45:26"}
|
| 82 |
+
{"current_steps": 800, "total_steps": 1182, "loss": 0.4726, "learning_rate": 5e-06, "epoch": 2.030456852791878, "percentage": 67.68, "elapsed_time": "1:32:36", "remaining_time": "0:44:13"}
|
| 83 |
+
{"current_steps": 810, "total_steps": 1182, "loss": 0.4689, "learning_rate": 5e-06, "epoch": 2.0558375634517767, "percentage": 68.53, "elapsed_time": "1:33:38", "remaining_time": "0:43:00"}
|